

浏览全部资源
扫码关注微信
1.华南理工大学电力学院,广东省广州市 510640
2.广东省电网智能量测与先进计量企业重点实验室,广东省广州市 510640
Received:24 March 2023,
Revised:2023-08-04,
Published Online:18 October 2023,
Published:25 January 2024
移动端阅览
刘熙鹏,罗庆全,余涛等.基于多尺度特征融合的负荷辨识及其可解释交互增强方法[J].电力系统自动化,2024,48(2):105-117.
LIU Xipeng,LUO Qingquan,YU Tao,et al.Load Identification and Its Interpretable Interactive Enhancement Method Based on Multi-scale Feature Fusion[J].Automation of Electric Power Systems,2024,48(2):105-117.
刘熙鹏,罗庆全,余涛等.基于多尺度特征融合的负荷辨识及其可解释交互增强方法[J].电力系统自动化,2024,48(2):105-117. DOI: 10.7500/AEPS20230324001.
LIU Xipeng,LUO Qingquan,YU Tao,et al.Load Identification and Its Interpretable Interactive Enhancement Method Based on Multi-scale Feature Fusion[J].Automation of Electric Power Systems,2024,48(2):105-117. DOI: 10.7500/AEPS20230324001.
负荷辨识技术可快速辨识电器类型,在家庭能量管理、危险用电预警、响应潜力评估等方面具有重要作用。针对现有负荷辨识方法多关注负荷长期或短期单尺度特征,导致特征表征能力不足而使模型识别精度和泛化性能受限的问题,提出一种基于多尺度特征融合的负荷辨识及其可解释交互增强方法。首先
从负荷采样数据中提取高频尺度的短期特征和中、低频尺度的长期特征,构建双塔结构的深层特征提取网络以利用网络的不同分支高效率挖掘各尺度深层特征。其次,设计自注意力与交叉注意力相结合的特征融合网络以实现负荷长、短期特征融合,提高模型的特征利用程度。然后,采用度量学习的训练方法,拉近同类型样本的特征距离,提升特征融合的效率和效果。最后,利用基于梯度的可解释分析方法量化特征的重要性,实现自适应的特征增强与结合专家交互的模型调优。实验结果说明所提模型识别精度与泛化能力均优于现有模型,且可解释分析验证了其有效性源于多尺度特征的充分利用。
Load identification technology can quickly identify the types of electrical appliances
and plays an important role in household energy management
hazardous warning
response potential assessment and other aspects. Aiming at the problem that the existing load identification methods focus on the long-term or short-term single-scale load features
resulting in insufficient feature representation capabilities
and thus limiting model identification accuracy and generalization performance
a load identification and its interpretable interactive enhancement method based on multi-scale feature fusion is proposed. Firstly
short-term features of high-frequency scale and long-term features of medium- and low-frequency scales are extracted from the load sampling data
and a deep feature extraction network with a double-tower structure is constructed to efficiently mine deep features of each scale by using different branches of the network. Secondly
a feature fusion network combining self-attention and cross-attention is designed to fuse long-term and short-term features
improving the feature utilization of the model. Then
a training method of metric learning is used to shorten the feature distance of the same type of samples and improve the efficiency and effect of feature fusion. Finally
the interpretable analysis method based on gradient is used to quantify the importance of features
and realize the adaptive feature enhancement and model optimization combined with expert interaction. The experimental results show that the recognition accuracy and generalization ability of the proposed model are superior to those of existing models
and the interpretable analysis verifies that its effectiveness comes from the full use of multi-scale features.
肖先勇 , 郑子萱 . “双碳”目标下新能源为主体的新型电力系统:贡献、关键技术与挑战 [J]. 工程科学与技术 , 2022 , 54 ( 1 ): 47 - 59 .
XIAO Xianyong , ZHENG Zixuan . New power systems dominated by renewable energy towards the goal of emission peak & carbon neutrality: contribution, key techniques, and challenges [J]. Advanced Engineering Sciences , 2022 , 54 ( 1 ): 47 - 59 .
ZHUANG M M , SHAHIDEHPOUR M , LI Z Y . An overview of non-intrusive load monitoring: approaches, business applications, and challenges [C]// International Conference on Power System Technology (POWERCON) , November 6-8 , 2018 , Guangzhou, China : 4291 - 4299 .
REHMAN A U , TITO S R , NIEWOULDT P , et al . Applications of non-intrusive load monitoring towards smart and sustainable future power grids: a system perspective [C]// 29th Australasian Universities Power Engineering Conference (AUPEC) , November 26-29 , 2019 , Nadi, Fiji : 1 - 6 .
王彩霞 , 时智勇 , 梁志峰 , 等 . 新能源为主体电力系统的需求侧资源利用关键技术及展望 [J]. 电力系统自动化 , 2021 , 45 ( 16 ): 37 - 48 .
WANG Caixia , SHI Zhiyong , LIANG Zhifeng , et al . Key technologies and prospects of demand-side resource utilization for power systems dominated by renewable energy [J]. Automation of Electric Power Systems , 2021 , 45 ( 16 ): 37 - 48 .
MARI S , BUCCI G , CIANCETTA F , et al . A review of non-intrusive load monitoring applications in industrial and residential contexts [J]. Energies , 2022 , 15 ( 23 ): 9011 .
SCHIRMER P A , MPORAS I . Non-intrusive load monitoring: a review [J]. IEEE Transactions on Smart Grid , 2023 , 14 ( 1 ): 769 - 784 .
HIMEUR Y , ALSALEMI A , BENSAALI F , et al . Effective non-intrusive load monitoring of buildings based on a novel multi-descriptor fusion with dimensionality reduction [J]. Applied Energy , 2020 , 279 : 115872 .
SADEGHIANPOURHAMAMI N , RUYSSINCK J , DESCHRIJVER D , et al . Comprehensive feature selection for appliance classification in NILM [J]. Energy and Buildings , 2017 , 151 : 98 - 106 .
ANGELIS G F , TIMPLALEXIS C , KRINIDIS S , et al . NILM applications: literature review of learning approaches, recent developments and challenges [J]. Energy and Buildings , 2022 , 261 : 111951 .
刘宇 , 刘丛笑 , 赵欣 , 等 . 基于维特比算法改进的稳暂态混合非侵入式负荷识别方法 [J/OL]. 电工技术学报 : 1 - 16 [ 2023-04-26 ]. https://doi.org/10.19595/j.cnki.1000-6753.tces.220566 https://doi.org/10.19595/j.cnki.1000-6753.tces.220566 .
LIU Yu , LIU Congxiao , ZHAO Xin , et al . An improved steady- and transient-state mixed non-intrusive load monitoring using Viterbi algorithm [J/OL]. Transactions of China Electrotechnical Society : 1 - 16 [ 2023-04-26 ]. https://doi.org/10.19595/j.cnki.1000-6753.tces.220566 https://doi.org/10.19595/j.cnki.1000-6753.tces.220566 .
RUOYUAN Z , MA R L . Non-invasive load identification method based on ABC-SVM algorithm and transient feature [J]. Energy Reports , 2022 , 8 : 63 - 72 .
ZHOU Z J , XIANG Y M , XU H , et al . A novel transfer learning-based intelligent nonintrusive load-monitoring with limited measurements [J]. IEEE Transactions on Instrumentation and Measurement , 2021 , 70 : 1 - 8 .
TUNDIS A , FAIZAN A , MÜHLHÄUSER M . A feature-based model for the identification of electrical devices in smart environments [J]. Sensors , 2019 , 19 ( 11 ): 2611 .
TEKLER Z D , LOW R , ZHOU Y R , et al . Near-real-time plug load identification using low-frequency power data in office spaces: experiments and applications [J]. Applied Energy , 2020 , 275 : 115391 .
武昕 , 严萌 , 郭一凡 , 等 . 基于结构化特征图谱的组合支持向量机非侵入式负荷辨识 [J]. 电力系统自动化 , 2022 , 46 ( 12 ): 210 - 219 .
WU Xin , YAN Meng , GUO Yifan , et al . Non-intrusive load identification by combined support vector machine based on structured characteristic spectrum [J]. Automation of Electric Power Systems , 2022 , 46 ( 12 ): 210 - 219 .
施雨松 , 徐青山 , 郑建 . 基于特征选择与增量学习的非侵入式电动自行车充电辨识方法 [J]. 电力系统自动化 , 2021 , 45 ( 7 ): 87 - 94 .
SHI Yusong , XU Qingshan , ZHENG Jian . Non-intrusive charging identification method for electric bicycles based on feature selection and incremental learning [J]. Automation of Electric Power Systems , 2021 , 45 ( 7 ): 87 - 94 .
KAHL M , HAQ A U , KRIECHBAUMER T , et al . A comprehensive feature study for appliance recognition on high frequency energy data [C]// 8th International Conference on Future Energy Systems , May 16-19 , 2017 , Hong Kong, China : 121 - 131 .
FAUSTINE A , PEREIRA L , KLEMENJAK C . Adaptive weighted recurrence graphs for appliance recognition in non-intrusive load monitoring [J]. IEEE Transactions on Smart Grid , 2021 , 12 ( 1 ): 398 - 406 .
SENARATHNA M , HERATH M , THILAKANAYAKE T D , et al . An image based approach of energy signal disaggregation using artificial intelligence [C]// IEEE 16th International Conference on Industrial and Information Systems (ICIIS) , December 9-11 , 2021 , Kandy, Sri Lanka : 98 - 103 .
ZHANG Y S , WU H , MA Q , et al . A learnable image-based load signature construction approach in NILM for appliances identification [J/OL]. IEEE Transactions on Smart Grid [ 2023-01-25 ]. https://ieeexplore.ieee.org/document/10025855 https://ieeexplore.ieee.org/document/10025855 .
DU L , HE D W , HARLEY R G , et al . Electric load classification by binary voltage-current trajectory mapping [J]. IEEE Transactions on Smart Grid , 2016 , 7 ( 1 ): 358 - 365 .
LIU Y C , WANG X , YOU W . Non-intrusive load monitoring by voltage-current trajectory enabled transfer learning [J]. IEEE Transactions on Smart Grid , 2019 , 10 ( 5 ): 5609 - 5619 .
解洋 , 梅飞 , 郑建勇 , 等 . 基于 V - I 轨迹颜色编码的非侵入式负荷识别方法 [J]. 电力系统自动化 , 2022 , 46 ( 4 ): 93 - 102 .
XIE Yang , MEI Fei , ZHENG Jianyong , et al . Non-intrusive load monitoring method based on V - I trajectory color coding [J]. Automation of Electric Power Systems , 2022 , 46 ( 4 ): 93 - 102 .
HAN Y H , LI K K , FENG H T , et al . Non-intrusive load monitoring based on semi-supervised smooth teacher graph learning with voltage-current trajectory [J]. Neural Computing and Applications , 2022 , 34 ( 21 ): 19147 - 19160 .
YU H Y , XU C J , GENG G C , et al . Multi-time-scale shapelet based feature extraction for non-intrusive load monitoring [J/OL]. IEEE Transactions on Smart Grid [ 2023-06-12 ]. https://ieeexplore.ieee.org/document/10147903 https://ieeexplore.ieee.org/document/10147903 .
LI Y Z , WANG H X , YANG J Y , et al . A non-intrusive load monitoring algorithm based on multiple features and decision fusion [J]. Energy Reports , 2021 , 7 : 1555 - 1562 .
王守相 , 郭陆阳 , 陈海文 , 等 . 基于特征融合与深度学习的非侵入式负荷辨识算法 [J]. 电力系统自动化 , 2020 , 44 ( 9 ): 103 - 110 .
WANG Shouxiang , GUO Luyang , CHEN Haiwen , et al . Non-intrusive load identification algorithm based on feature fusion and deep learning [J]. Automation of Electric Power Systems , 2020 , 44 ( 9 ): 103 - 110 .
乔骥 , 郭剑波 , 范士雄 , 等 . 人在回路的电网调控混合增强智能初探:基本概念与研究框架 [J]. 中国电机工程学报 , 2023 , 43 ( 1 ): 1 - 15 .
QIAO Ji , GUO Jianbo , FAN Shixiong , et al . Human-in-the-loop hybrid-augmented intelligence method for power system dispatching: basic concept and research framework [J]. Proceedings of the CSEE , 2023 , 43 ( 1 ): 1 - 15 .
姚建国 , 余涛 , 杨胜春 , 等 . 提升电网调度中人工智能可用性的混合增强智能知识演化技术 [J]. 电力系统自动化 , 2022 , 46 ( 20 ): 1 - 12 .
YAO Jianguo , YU Tao , YANG Shengchun , et al . Knowledge evolution technology based on hybrid-augmented intelligence for improving practicability of artificial intelligence in power grid dispatch [J]. Automation of Electric Power Systems , 2022 , 46 ( 20 ): 1 - 12 .
武宇翔 , 韩肖清 , 牛哲文 , 等 . 基于变权重随机森林的暂态稳定评估方法及其可解释性分析 [J]. 电力系统自动化 , 2023 , 47 ( 14 ): 93 - 104 .
WU Yuxiang , HAN Xiaoqing , NIU Zhewen , et al . Transient stability assessment method based on variable weight random forest and its interpretability analysis [J]. Automation of Electric Power Systems , 2023 , 47 ( 14 ): 93 - 104 .
古思丽 , 乔骥 , 张东霞 , 等 . 基于图深度学习的薄弱支路辨识与溯因分析 [J]. 中国电机工程学报 , 2023 , 43 ( 3 ): 1004 - 1017 .
GU Sili , QIAO Ji , ZHANG Dongxia , et al . Weak branch identification and retrospective analysis based on graph depth learning [J]. Proceedings of the CSEE , 2023 , 43 ( 3 ): 1004 - 1017 .
YI X Y , YANG J , HONG L C , et al . Sampling-bias-corrected neural modeling for large corpus item recommendations [C]// 13th ACM Conference on Recommender Systems , September 16-20 , 2019 , Copenhagen, Denmark : 269 - 277 .
RADFORD A , KIM J W , HALLACY C , et al . Learning transferable visual models from natural language supervision [EB/OL]. [ 2022-10-05 ]. https://arxiv.org/abs/2103.00020 https://arxiv.org/abs/2103.00020 .
CHEN J F , WANG X , ZHANG X T , et al . Temporal and spectral feature learning with two-stream convolutional neural networks for appliance recognition in NILM [J]. IEEE Transactions on Smart Grid , 2022 , 13 ( 1 ): 762 - 772 .
DEVLIN J , CHANG M W , LEE K , et al . BERT: pre-training of deep bidirectional transformers for language understanding [EB/OL]. [ 2022-10-05 ]. https://arxiv.org/abs/1810.04805 https://arxiv.org/abs/1810.04805 .
DOSOVITSKIY A , BEYER L , KOLESNIKOV A , et al . An image is worth 16 × 16 words: transformers for image recognition at scale[EB/OL]. [ 2022-10-05 ]. https://arxiv.org/abs/2010.11929 https://arxiv.org/abs/2010.11929 .
KAYA , BILGE . Deep metric learning: a survey [J]. Symmetry , 2019 , 11 ( 9 ): 1066 .
LUO Q Q , YU T , LAN C F , et al . A generalizable method for practical non-intrusive load monitoring via metric-based meta-learning [J/OL]. IEEE Transactions on Smart Grid [ 2023-03-31 ]. https://ieeexplore.ieee.org/document/10090473 https://ieeexplore.ieee.org/document/10090473 .
CHATTOPADHAY A , SARKAR A , HOWLADER P , et al . Grad-CAM: generalized gradient-based visual explanations for deep convolutional networks [C]// IEEE Winter Conference on Applications of Computer Vision (WACV) , March 12-15 , 2018 , Lake Tahoe, USA : 839 - 847 .
牛卢璐 , 贾宏杰 . 一种适用于非侵入式负荷监测的暂态事件检测算法 [J]. 电力系统自动化 , 2011 , 35 ( 9 ): 30 - 35 .
NIU Lulu , JIA Hongjie . Transient event detection algorithm for non-intrusive load monitoring [J]. Automation of Electric Power Systems , 2011 , 35 ( 9 ): 30 - 35 .
曹华珍 , 吴亚雄 , 李浩 , 等 . 基于海量数据的多维度负荷特性分析系统开发 [J]. 电力系统保护与控制 , 2021 , 49 ( 6 ): 155 - 166 .
CAO Huazhen , WU Yaxiong , LI Hao , et al . Development of a multi-dimensional load characteristic analysis system based on massive data [J]. Power System Protection and Control , 2021 , 49 ( 6 ): 155 - 166 .
VASWANI A , SHAZEER N , PARMAR N , et al . Attention is all you need [C]// 31st International Conference on Neural Information Processing Systems , December 4-9 , 2017 , Long Beach, USA : 6000 - 6010 .
HOU Z , YU B S , TAO D C . BatchFormer: learning to explore sample relationships for robust representation learning [C]// IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , June 18-24 , 2022 , New Orleans, USA : 7246 - 7256 .
WU C Y , MANMATHA R , SMOLA A J , et al . Sampling matters in deep embedding learning [C]// IEEE International Conference on Computer Vision (ICCV) , October 22-29 , 2017 , Venice, Italy : 2859 - 2867 .
CIPOLLA R , GAL Y , KENDALL A . Multi-task learning using uncertainty to weigh losses for scene geometry and semantics [C]// IEEE/CVF Conference on Computer Vision and Pattern Recognition , June 18-23 , 2018 , Salt Lake City, USA : 7482 - 7491 .
KRIECHBAUMER T , JACOBSEN H A . BLOND, a building-level office environment dataset of typical electrical appliances [J]. Scientific Data , 2018 , 5 : 180048 .
FILIP A . Blued: a fully labeled public dataset for event-based nonintrusive load monitoring research [C]// 2nd Workshop on Data Mining Applications in Sustainability (SustKDD) , August 12 , 2012, Beijing , China .
D’INCECCO M , SQUARTINI S , ZHONG M J . Transfer learning for non-intrusive load monitoring [J]. IEEE Transactions on Smart Grid , 2020 , 11 ( 2 ): 1419 - 1429 .
LI D D , LI J F , ZENG X , et al . Transfer learning for multi-objective non-intrusive load monitoring in smart building [J]. Applied Energy , 2023 , 329 : 120223 .
ZHANG Y , TANG G M , HUANG Q Y , et al . FedNILM: applying federated learning to NILM applications at the edge [J]. IEEE Transactions on Green Communications and Networking , 2023 , 7 ( 2 ): 857 - 868 .
NGUYEN V K , ZHANG W E , MAHMOOD A . Semi-supervised intrusive appliance load monitoring in smart energy monitoring system [J]. ACM Transactions on Sensor Networks , 17 ( 3 ): 32 .
0
Views
0
下载量
1
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution
京公网安备11010802024621